Instructions to use AgenticFinLab/PyFi-QwenVL-7B-COT-47K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use AgenticFinLab/PyFi-QwenVL-7B-COT-47K with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/home/yuxuanzhao/LLaMA-Factory/models/qwen2_5-vl-7B-Instruct") model = PeftModel.from_pretrained(base_model, "AgenticFinLab/PyFi-QwenVL-7B-COT-47K") - Transformers
How to use AgenticFinLab/PyFi-QwenVL-7B-COT-47K with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AgenticFinLab/PyFi-QwenVL-7B-COT-47K") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("AgenticFinLab/PyFi-QwenVL-7B-COT-47K", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use AgenticFinLab/PyFi-QwenVL-7B-COT-47K with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AgenticFinLab/PyFi-QwenVL-7B-COT-47K" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AgenticFinLab/PyFi-QwenVL-7B-COT-47K", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/AgenticFinLab/PyFi-QwenVL-7B-COT-47K
- SGLang
How to use AgenticFinLab/PyFi-QwenVL-7B-COT-47K with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "AgenticFinLab/PyFi-QwenVL-7B-COT-47K" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AgenticFinLab/PyFi-QwenVL-7B-COT-47K", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "AgenticFinLab/PyFi-QwenVL-7B-COT-47K" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AgenticFinLab/PyFi-QwenVL-7B-COT-47K", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use AgenticFinLab/PyFi-QwenVL-7B-COT-47K with Docker Model Runner:
docker model run hf.co/AgenticFinLab/PyFi-QwenVL-7B-COT-47K
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1473, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00679001867255135, | |
| "grad_norm": 0.3864942491054535, | |
| "learning_rate": 6.081081081081082e-06, | |
| "loss": 1.15, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0135800373451027, | |
| "grad_norm": 0.4518967866897583, | |
| "learning_rate": 1.2837837837837838e-05, | |
| "loss": 1.1633, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02037005601765405, | |
| "grad_norm": 0.36683163046836853, | |
| "learning_rate": 1.9594594594594595e-05, | |
| "loss": 1.1004, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0271600746902054, | |
| "grad_norm": 0.2317497730255127, | |
| "learning_rate": 2.635135135135135e-05, | |
| "loss": 1.014, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03395009336275675, | |
| "grad_norm": 0.2007765769958496, | |
| "learning_rate": 3.310810810810811e-05, | |
| "loss": 0.9387, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0407401120353081, | |
| "grad_norm": 0.19630813598632812, | |
| "learning_rate": 3.986486486486487e-05, | |
| "loss": 0.8715, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.04753013070785945, | |
| "grad_norm": 0.20267479121685028, | |
| "learning_rate": 4.662162162162162e-05, | |
| "loss": 0.8385, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0543201493804108, | |
| "grad_norm": 0.21056681871414185, | |
| "learning_rate": 5.337837837837838e-05, | |
| "loss": 0.7904, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06111016805296215, | |
| "grad_norm": 0.181947723031044, | |
| "learning_rate": 6.013513513513514e-05, | |
| "loss": 0.7601, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0679001867255135, | |
| "grad_norm": 0.1922345757484436, | |
| "learning_rate": 6.68918918918919e-05, | |
| "loss": 0.7673, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07469020539806484, | |
| "grad_norm": 0.18776988983154297, | |
| "learning_rate": 7.364864864864865e-05, | |
| "loss": 0.7375, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0814802240706162, | |
| "grad_norm": 0.2282622903585434, | |
| "learning_rate": 8.040540540540541e-05, | |
| "loss": 0.7381, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.08827024274316754, | |
| "grad_norm": 0.2738005220890045, | |
| "learning_rate": 8.716216216216216e-05, | |
| "loss": 0.7237, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.0950602614157189, | |
| "grad_norm": 0.21742618083953857, | |
| "learning_rate": 9.391891891891892e-05, | |
| "loss": 0.7023, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.10185028008827024, | |
| "grad_norm": 0.25216951966285706, | |
| "learning_rate": 9.999985945746134e-05, | |
| "loss": 0.7101, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1086402987608216, | |
| "grad_norm": 0.25243276357650757, | |
| "learning_rate": 9.998299530880787e-05, | |
| "loss": 0.687, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.11543031743337294, | |
| "grad_norm": 0.3072853684425354, | |
| "learning_rate": 9.993803351513094e-05, | |
| "loss": 0.7097, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.1222203361059243, | |
| "grad_norm": 0.2733334004878998, | |
| "learning_rate": 9.986499935143679e-05, | |
| "loss": 0.6722, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.12901035477847564, | |
| "grad_norm": 0.2821713387966156, | |
| "learning_rate": 9.976393387344834e-05, | |
| "loss": 0.6935, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.135800373451027, | |
| "grad_norm": 0.28884661197662354, | |
| "learning_rate": 9.963489389452596e-05, | |
| "loss": 0.6964, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14259039212357835, | |
| "grad_norm": 0.25266194343566895, | |
| "learning_rate": 9.947795195373016e-05, | |
| "loss": 0.6926, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.14938041079612968, | |
| "grad_norm": 0.3153521418571472, | |
| "learning_rate": 9.92931962750442e-05, | |
| "loss": 0.6727, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.15617042946868104, | |
| "grad_norm": 0.29505372047424316, | |
| "learning_rate": 9.908073071777954e-05, | |
| "loss": 0.6814, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.1629604481412324, | |
| "grad_norm": 0.2789740562438965, | |
| "learning_rate": 9.884067471819184e-05, | |
| "loss": 0.6817, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.16975046681378375, | |
| "grad_norm": 0.2661297917366028, | |
| "learning_rate": 9.857316322234067e-05, | |
| "loss": 0.6795, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.17654048548633508, | |
| "grad_norm": 0.2866443395614624, | |
| "learning_rate": 9.827834661023034e-05, | |
| "loss": 0.6623, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.18333050415888644, | |
| "grad_norm": 0.2814137637615204, | |
| "learning_rate": 9.795639061127468e-05, | |
| "loss": 0.6606, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.1901205228314378, | |
| "grad_norm": 0.30371809005737305, | |
| "learning_rate": 9.760747621113325e-05, | |
| "loss": 0.6679, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.19691054150398912, | |
| "grad_norm": 0.311916321516037, | |
| "learning_rate": 9.723179954997125e-05, | |
| "loss": 0.6817, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.20370056017654048, | |
| "grad_norm": 0.2893620431423187, | |
| "learning_rate": 9.682957181220062e-05, | |
| "loss": 0.6678, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.21049057884909184, | |
| "grad_norm": 0.3415584862232208, | |
| "learning_rate": 9.640101910776381e-05, | |
| "loss": 0.6512, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.2172805975216432, | |
| "grad_norm": 0.2780122756958008, | |
| "learning_rate": 9.594638234502753e-05, | |
| "loss": 0.6454, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.22407061619419452, | |
| "grad_norm": 0.28491947054862976, | |
| "learning_rate": 9.546591709535751e-05, | |
| "loss": 0.6597, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.23086063486674588, | |
| "grad_norm": 0.28796347975730896, | |
| "learning_rate": 9.495989344945056e-05, | |
| "loss": 0.6515, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.23765065353929724, | |
| "grad_norm": 0.2798394560813904, | |
| "learning_rate": 9.442859586550468e-05, | |
| "loss": 0.654, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.2444406722118486, | |
| "grad_norm": 0.31528720259666443, | |
| "learning_rate": 9.387232300931255e-05, | |
| "loss": 0.6477, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.2512306908843999, | |
| "grad_norm": 0.329709529876709, | |
| "learning_rate": 9.32913875863684e-05, | |
| "loss": 0.6576, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.2580207095569513, | |
| "grad_norm": 0.31941738724708557, | |
| "learning_rate": 9.268611616608236e-05, | |
| "loss": 0.6561, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.26481072822950263, | |
| "grad_norm": 0.30430927872657776, | |
| "learning_rate": 9.205684899820147e-05, | |
| "loss": 0.6453, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.271600746902054, | |
| "grad_norm": 0.31718093156814575, | |
| "learning_rate": 9.140393982154026e-05, | |
| "loss": 0.6434, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.27839076557460535, | |
| "grad_norm": 0.30542615056037903, | |
| "learning_rate": 9.072775566512863e-05, | |
| "loss": 0.6355, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.2851807842471567, | |
| "grad_norm": 0.3371242880821228, | |
| "learning_rate": 9.002867664188858e-05, | |
| "loss": 0.6565, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.291970802919708, | |
| "grad_norm": 0.30639946460723877, | |
| "learning_rate": 8.930709573495602e-05, | |
| "loss": 0.6525, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.29876082159225936, | |
| "grad_norm": 0.29678982496261597, | |
| "learning_rate": 8.856341857676758e-05, | |
| "loss": 0.6435, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.3055508402648107, | |
| "grad_norm": 0.295890748500824, | |
| "learning_rate": 8.779806322103682e-05, | |
| "loss": 0.6458, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.3123408589373621, | |
| "grad_norm": 0.39472854137420654, | |
| "learning_rate": 8.701145990774775e-05, | |
| "loss": 0.6582, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.31913087760991343, | |
| "grad_norm": 0.3048432469367981, | |
| "learning_rate": 8.620405082129798e-05, | |
| "loss": 0.6482, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.3259208962824648, | |
| "grad_norm": 0.30375346541404724, | |
| "learning_rate": 8.537628984192736e-05, | |
| "loss": 0.6473, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.33271091495501615, | |
| "grad_norm": 0.3189581036567688, | |
| "learning_rate": 8.452864229057191e-05, | |
| "loss": 0.6423, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.3395009336275675, | |
| "grad_norm": 0.30964285135269165, | |
| "learning_rate": 8.366158466728644e-05, | |
| "loss": 0.6239, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3462909523001188, | |
| "grad_norm": 0.30495893955230713, | |
| "learning_rate": 8.277560438338278e-05, | |
| "loss": 0.6307, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.35308097097267016, | |
| "grad_norm": 0.3121732175350189, | |
| "learning_rate": 8.18711994874345e-05, | |
| "loss": 0.6363, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.3598709896452215, | |
| "grad_norm": 0.32421112060546875, | |
| "learning_rate": 8.094887838530174e-05, | |
| "loss": 0.636, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.3666610083177729, | |
| "grad_norm": 0.3044915497303009, | |
| "learning_rate": 8.000915955433396e-05, | |
| "loss": 0.6276, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.37345102699032423, | |
| "grad_norm": 0.3056237995624542, | |
| "learning_rate": 7.905257125191094e-05, | |
| "loss": 0.627, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.3802410456628756, | |
| "grad_norm": 0.29212453961372375, | |
| "learning_rate": 7.807965121848597e-05, | |
| "loss": 0.6295, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.38703106433542694, | |
| "grad_norm": 0.2936370074748993, | |
| "learning_rate": 7.70909463752983e-05, | |
| "loss": 0.6449, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.39382108300797825, | |
| "grad_norm": 0.3245689868927002, | |
| "learning_rate": 7.608701251692457e-05, | |
| "loss": 0.6506, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.4006111016805296, | |
| "grad_norm": 0.33466264605522156, | |
| "learning_rate": 7.506841399884217e-05, | |
| "loss": 0.6217, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.40740112035308096, | |
| "grad_norm": 0.3045268952846527, | |
| "learning_rate": 7.403572342018021e-05, | |
| "loss": 0.6284, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.4141911390256323, | |
| "grad_norm": 0.31157055497169495, | |
| "learning_rate": 7.29895213018362e-05, | |
| "loss": 0.6459, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.4209811576981837, | |
| "grad_norm": 0.30077850818634033, | |
| "learning_rate": 7.193039576013976e-05, | |
| "loss": 0.638, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.42777117637073503, | |
| "grad_norm": 0.31292667984962463, | |
| "learning_rate": 7.085894217624645e-05, | |
| "loss": 0.6411, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.4345611950432864, | |
| "grad_norm": 0.30501753091812134, | |
| "learning_rate": 6.977576286144784e-05, | |
| "loss": 0.6177, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.44135121371583774, | |
| "grad_norm": 0.32817915081977844, | |
| "learning_rate": 6.868146671858567e-05, | |
| "loss": 0.624, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.44814123238838904, | |
| "grad_norm": 0.3311234414577484, | |
| "learning_rate": 6.757666889976085e-05, | |
| "loss": 0.6319, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.4549312510609404, | |
| "grad_norm": 0.3192739486694336, | |
| "learning_rate": 6.646199046052921e-05, | |
| "loss": 0.6193, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.46172126973349176, | |
| "grad_norm": 0.29953694343566895, | |
| "learning_rate": 6.533805801077899e-05, | |
| "loss": 0.615, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.4685112884060431, | |
| "grad_norm": 0.32995176315307617, | |
| "learning_rate": 6.420550336248558e-05, | |
| "loss": 0.6357, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.47530130707859447, | |
| "grad_norm": 0.29778003692626953, | |
| "learning_rate": 6.306496317454227e-05, | |
| "loss": 0.6164, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.4820913257511458, | |
| "grad_norm": 0.3111869990825653, | |
| "learning_rate": 6.191707859486622e-05, | |
| "loss": 0.6133, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.4888813444236972, | |
| "grad_norm": 0.32019391655921936, | |
| "learning_rate": 6.076249489998097e-05, | |
| "loss": 0.6243, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.49567136309624854, | |
| "grad_norm": 0.323253870010376, | |
| "learning_rate": 5.9601861132278e-05, | |
| "loss": 0.6253, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.5024613817687998, | |
| "grad_norm": 0.3075142800807953, | |
| "learning_rate": 5.8435829735161416e-05, | |
| "loss": 0.6129, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.5092514004413512, | |
| "grad_norm": 0.34016624093055725, | |
| "learning_rate": 5.7265056186280754e-05, | |
| "loss": 0.6381, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.5160414191139026, | |
| "grad_norm": 0.34157323837280273, | |
| "learning_rate": 5.6090198629058134e-05, | |
| "loss": 0.6211, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.5228314377864539, | |
| "grad_norm": 0.29887712001800537, | |
| "learning_rate": 5.491191750271677e-05, | |
| "loss": 0.6132, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.5296214564590053, | |
| "grad_norm": 0.32949894666671753, | |
| "learning_rate": 5.373087517101899e-05, | |
| "loss": 0.6296, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.5364114751315566, | |
| "grad_norm": 0.33202993869781494, | |
| "learning_rate": 5.254773554992242e-05, | |
| "loss": 0.6195, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.543201493804108, | |
| "grad_norm": 0.3175908029079437, | |
| "learning_rate": 5.136316373436343e-05, | |
| "loss": 0.6203, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.5499915124766593, | |
| "grad_norm": 0.33497434854507446, | |
| "learning_rate": 5.0177825624378114e-05, | |
| "loss": 0.6257, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.5567815311492107, | |
| "grad_norm": 0.3095554709434509, | |
| "learning_rate": 4.8992387550770373e-05, | |
| "loss": 0.6174, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.563571549821762, | |
| "grad_norm": 0.3134996294975281, | |
| "learning_rate": 4.780751590053813e-05, | |
| "loss": 0.6041, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.5703615684943134, | |
| "grad_norm": 0.34364205598831177, | |
| "learning_rate": 4.662387674226771e-05, | |
| "loss": 0.6102, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.5771515871668647, | |
| "grad_norm": 0.3402939438819885, | |
| "learning_rate": 4.544213545170741e-05, | |
| "loss": 0.6238, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.583941605839416, | |
| "grad_norm": 0.3603513240814209, | |
| "learning_rate": 4.4262956337730385e-05, | |
| "loss": 0.6338, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.5907316245119674, | |
| "grad_norm": 0.3301768898963928, | |
| "learning_rate": 4.3087002268897434e-05, | |
| "loss": 0.6249, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.5975216431845187, | |
| "grad_norm": 0.32261279225349426, | |
| "learning_rate": 4.191493430082929e-05, | |
| "loss": 0.6174, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.6043116618570701, | |
| "grad_norm": 0.3522423505783081, | |
| "learning_rate": 4.074741130459813e-05, | |
| "loss": 0.6227, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.6111016805296214, | |
| "grad_norm": 0.3201356828212738, | |
| "learning_rate": 3.9585089596347094e-05, | |
| "loss": 0.6335, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.6178916992021728, | |
| "grad_norm": 0.3597421944141388, | |
| "learning_rate": 3.842862256834613e-05, | |
| "loss": 0.6325, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.6246817178747242, | |
| "grad_norm": 0.30802375078201294, | |
| "learning_rate": 3.727866032169127e-05, | |
| "loss": 0.6161, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.6314717365472755, | |
| "grad_norm": 0.3393535912036896, | |
| "learning_rate": 3.6135849300854225e-05, | |
| "loss": 0.6192, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.6382617552198269, | |
| "grad_norm": 0.3308396339416504, | |
| "learning_rate": 3.500083193028741e-05, | |
| "loss": 0.6138, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.6450517738923782, | |
| "grad_norm": 0.33988067507743835, | |
| "learning_rate": 3.387424625328892e-05, | |
| "loss": 0.6113, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.6518417925649296, | |
| "grad_norm": 0.3523455262184143, | |
| "learning_rate": 3.275672557333015e-05, | |
| "loss": 0.6162, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.6586318112374809, | |
| "grad_norm": 0.3228614628314972, | |
| "learning_rate": 3.164889809804808e-05, | |
| "loss": 0.6062, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.6654218299100323, | |
| "grad_norm": 0.311490923166275, | |
| "learning_rate": 3.055138658610202e-05, | |
| "loss": 0.607, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.6722118485825836, | |
| "grad_norm": 0.33996137976646423, | |
| "learning_rate": 2.946480799709358e-05, | |
| "loss": 0.6144, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.679001867255135, | |
| "grad_norm": 0.3363693952560425, | |
| "learning_rate": 2.83897731447464e-05, | |
| "loss": 0.6031, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.6857918859276863, | |
| "grad_norm": 0.32421648502349854, | |
| "learning_rate": 2.7326886353540916e-05, | |
| "loss": 0.6148, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.6925819046002376, | |
| "grad_norm": 0.3457362949848175, | |
| "learning_rate": 2.627674511899678e-05, | |
| "loss": 0.6169, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.699371923272789, | |
| "grad_norm": 0.3354722261428833, | |
| "learning_rate": 2.5239939771794563e-05, | |
| "loss": 0.6158, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.7061619419453403, | |
| "grad_norm": 0.4128516614437103, | |
| "learning_rate": 2.421705314592452e-05, | |
| "loss": 0.6138, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.7129519606178917, | |
| "grad_norm": 0.3348320722579956, | |
| "learning_rate": 2.3208660251050158e-05, | |
| "loss": 0.6089, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.719741979290443, | |
| "grad_norm": 0.36343589425086975, | |
| "learning_rate": 2.2215327949269886e-05, | |
| "loss": 0.6155, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.7265319979629944, | |
| "grad_norm": 0.3468243479728699, | |
| "learning_rate": 2.123761463645878e-05, | |
| "loss": 0.6282, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.7333220166355457, | |
| "grad_norm": 0.37657150626182556, | |
| "learning_rate": 2.0276069928369746e-05, | |
| "loss": 0.6094, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.7401120353080971, | |
| "grad_norm": 0.3502194583415985, | |
| "learning_rate": 1.933123435167018e-05, | |
| "loss": 0.6191, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.7469020539806485, | |
| "grad_norm": 0.3248715102672577, | |
| "learning_rate": 1.840363904008819e-05, | |
| "loss": 0.6099, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.7536920726531998, | |
| "grad_norm": 0.33478298783302307, | |
| "learning_rate": 1.7493805435838874e-05, | |
| "loss": 0.6126, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.7604820913257512, | |
| "grad_norm": 0.3416365385055542, | |
| "learning_rate": 1.660224499649861e-05, | |
| "loss": 0.6202, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.7672721099983025, | |
| "grad_norm": 0.37717097997665405, | |
| "learning_rate": 1.5729458907492327e-05, | |
| "loss": 0.6179, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.7740621286708539, | |
| "grad_norm": 0.33141157031059265, | |
| "learning_rate": 1.4875937800354988e-05, | |
| "loss": 0.6101, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.7808521473434052, | |
| "grad_norm": 0.3471899926662445, | |
| "learning_rate": 1.404216147692598e-05, | |
| "loss": 0.6176, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.7876421660159565, | |
| "grad_norm": 0.349560409784317, | |
| "learning_rate": 1.3228598639631418e-05, | |
| "loss": 0.6166, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.7944321846885078, | |
| "grad_norm": 0.3692922592163086, | |
| "learning_rate": 1.2435706628005767e-05, | |
| "loss": 0.6067, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.8012222033610592, | |
| "grad_norm": 0.3713966906070709, | |
| "learning_rate": 1.1663931161601188e-05, | |
| "loss": 0.6105, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.8080122220336106, | |
| "grad_norm": 0.3440631031990051, | |
| "learning_rate": 1.0913706089428932e-05, | |
| "loss": 0.6, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.8148022407061619, | |
| "grad_norm": 0.35651665925979614, | |
| "learning_rate": 1.0185453146073604e-05, | |
| "loss": 0.6151, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.8215922593787133, | |
| "grad_norm": 0.4277671277523041, | |
| "learning_rate": 9.479581714617668e-06, | |
| "loss": 0.6116, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.8283822780512646, | |
| "grad_norm": 0.3536016345024109, | |
| "learning_rate": 8.796488596509133e-06, | |
| "loss": 0.6179, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.835172296723816, | |
| "grad_norm": 0.3368649184703827, | |
| "learning_rate": 8.136557788501903e-06, | |
| "loss": 0.6168, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.8419623153963673, | |
| "grad_norm": 0.3577621281147003, | |
| "learning_rate": 7.500160266794371e-06, | |
| "loss": 0.6163, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.8487523340689187, | |
| "grad_norm": 0.34164294600486755, | |
| "learning_rate": 6.887653778487307e-06, | |
| "loss": 0.6151, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.8555423527414701, | |
| "grad_norm": 0.3569304049015045, | |
| "learning_rate": 6.2993826404783965e-06, | |
| "loss": 0.6141, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.8623323714140214, | |
| "grad_norm": 0.37374386191368103, | |
| "learning_rate": 5.735677545906626e-06, | |
| "loss": 0.6161, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.8691223900865728, | |
| "grad_norm": 0.3596641719341278, | |
| "learning_rate": 5.196855378254989e-06, | |
| "loss": 0.6075, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.8759124087591241, | |
| "grad_norm": 0.35499128699302673, | |
| "learning_rate": 4.683219033216402e-06, | |
| "loss": 0.6001, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.8827024274316755, | |
| "grad_norm": 0.32738348841667175, | |
| "learning_rate": 4.1950572484226345e-06, | |
| "loss": 0.6094, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.8894924461042268, | |
| "grad_norm": 0.3689960539340973, | |
| "learning_rate": 3.7326444411321547e-06, | |
| "loss": 0.6119, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.8962824647767781, | |
| "grad_norm": 0.3303182125091553, | |
| "learning_rate": 3.2962405539681217e-06, | |
| "loss": 0.6084, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.9030724834493294, | |
| "grad_norm": 0.3562391698360443, | |
| "learning_rate": 2.8860909087931543e-06, | |
| "loss": 0.6103, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.9098625021218808, | |
| "grad_norm": 0.3637941777706146, | |
| "learning_rate": 2.5024260688030987e-06, | |
| "loss": 0.5962, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.9166525207944322, | |
| "grad_norm": 0.3294752240180969, | |
| "learning_rate": 2.145461708917312e-06, | |
| "loss": 0.6043, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.9234425394669835, | |
| "grad_norm": 0.35764122009277344, | |
| "learning_rate": 1.8153984945382452e-06, | |
| "loss": 0.6038, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.9302325581395349, | |
| "grad_norm": 0.35339877009391785, | |
| "learning_rate": 1.512421968748623e-06, | |
| "loss": 0.5948, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.9370225768120862, | |
| "grad_norm": 0.3505209982395172, | |
| "learning_rate": 1.2367024480094691e-06, | |
| "loss": 0.62, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.9438125954846376, | |
| "grad_norm": 0.3490634560585022, | |
| "learning_rate": 9.883949264176962e-07, | |
| "loss": 0.5942, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.9506026141571889, | |
| "grad_norm": 0.4094849228858948, | |
| "learning_rate": 7.676389885771518e-07, | |
| "loss": 0.6072, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.9573926328297403, | |
| "grad_norm": 0.3647181987762451, | |
| "learning_rate": 5.745587311318968e-07, | |
| "loss": 0.603, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.9641826515022917, | |
| "grad_norm": 0.3373996615409851, | |
| "learning_rate": 4.0926269300603503e-07, | |
| "loss": 0.6036, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.970972670174843, | |
| "grad_norm": 0.3408346176147461, | |
| "learning_rate": 2.71843794389226e-07, | |
| "loss": 0.6101, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.9777626888473944, | |
| "grad_norm": 0.361774742603302, | |
| "learning_rate": 1.623792845020955e-07, | |
| "loss": 0.5909, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.9845527075199457, | |
| "grad_norm": 0.3575396239757538, | |
| "learning_rate": 8.093069817109445e-08, | |
| "loss": 0.5922, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.9913427261924971, | |
| "grad_norm": 0.3574063181877136, | |
| "learning_rate": 2.7543821237030475e-08, | |
| "loss": 0.6109, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.9981327448650483, | |
| "grad_norm": 0.33741241693496704, | |
| "learning_rate": 2.2486648168396075e-09, | |
| "loss": 0.5931, | |
| "step": 1470 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1473, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.1892094394273628e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |